DIPAK VARPE

1. Project Title: Sales Analytics (All Birds)
Objective: Analyzed sales data to identify buyer preferences and inform business strategies.
Key Achievements:
• Conducted Exploratory Data Analysis (EDA) using Seaborn and Pandas.

• Utilized various visualizations including Countplot, Barplots, Histograms, and Pie charts.

• Identified Maharashtra as a significant market and highlighted high demand for T-shirts.

• Determined M-Size as the preferred choice among buyers.
Conclusion: Provided actionable insights for marketing and sales strategies, contributing to informed decision-making.

2. Project Title: Heart Disease Prediction using Machine Learning (EHR)
Objective: Developed a Machine Learning model to predict the presence of heart disease in individuals.
Key Achievements:
• Utilized Seaborn and Heatmap for feature selection.

• Identified the need to convert categorical variables into dummy variables and scale all values before training ML models.

• Employed the get_dummies method to create dummy columns for categorical variables.

• Experimented with two algorithms: KNeighborsClassifier and RandomForestClassifier.

• Evaluated model performance using cross_val_score.
Conclusion: Achieved scores exceeding 80%, indicating the model's ability to predict the presence of heart disease in individuals

3. Project Title: Delivery Time Prediction for Meal Services
Objective: Developed a model to accurately predict delivery times for meal services, tailored for the client, Cook Unity.
Key Achievements:
• Utilized scatter plots to identify relationships between features and delivery time.

• Identified key contributing factors: Age of delivery personnel (linear relationship), Ratings of delivery personnel (inverse linear relationship), Distance between restaurant and delivery location (consistent relationship).

• Trained a model using LSTM neural network.

• Successfully tested model performance by predicting delivery times.
Conclusion: Real-time delivery time prediction requires calculating distance between meal preparation and consumption points. Establishing relationships between past delivery times and distances is crucial for accurate predictions.

Responsibilities :
• Conducted EDA to uncover insights and trends, making data-driven recommendations.
• Developed predictive models for heart disease and food delivery times, deploying them for real-time decision-making.
• Engineered features to improve model performance.
• Cleaned and preprocessed data to ensure quality for analysis.
• Collaborated with stakeholders to translate project requirements into actionable solutions, communicating findings effectively.
• Designed experiments to evaluate model performance, iterating for continuous improvement.
• Created informative data visualizations to communicate insights effectively.
• Stayed updated with the latest developments in data science, applying new techniques to enhance project outcomes.